Generalized Disparate Impact for Configurable Fairness Solutions in ML
Luca Giuliani, Eleonora Misino, Michele Lombardi
Abstract
We make two contributions in the field of AI fairness over continuous protected attributes. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is valuable but subject to a few crucial limitations regarding semantics, interpretability, and robustness. Second, we introduce a family of indicators that are: 1) complementary to HGR in terms of semantics; 2) fully interpretable and transparent; 3) robust over finite samples; 4) configurable to suit specific applications. Our approach also allows us to define fine-grained constraints to permit certain types of dependence and forbid others selectively. By expanding the available options for continuous protected attributes, our approach represents a significant contribution to the area of fair artificial intelligence.
BibTeX
@inproceedings{icml2023_generalizeddispa,
title = {Generalized Disparate Impact for Configurable Fairness Solutions in ML},
author = {Luca Giuliani and Eleonora Misino and Michele Lombardi},
booktitle = {ICML 2023},
year = {2023}
}